English

Evaluating the COVID-19 Identification ResNet (CIdeR) on the INTERSPEECH COVID-19 from Audio Challenges

Sound 2021-08-02 v1 Machine Learning Audio and Speech Processing

Abstract

We report on cross-running the recent COVID-19 Identification ResNet (CIdeR) on the two Interspeech 2021 COVID-19 diagnosis from cough and speech audio challenges: ComParE and DiCOVA. CIdeR is an end-to-end deep learning neural network originally designed to classify whether an individual is COVID-positive or COVID-negative based on coughing and breathing audio recordings from a published crowdsourced dataset. In the current study, we demonstrate the potential of CIdeR at binary COVID-19 diagnosis from both the COVID-19 Cough and Speech Sub-Challenges of INTERSPEECH 2021, ComParE and DiCOVA. CIdeR achieves significant improvements over several baselines.

Keywords

Cite

@article{arxiv.2107.14549,
  title  = {Evaluating the COVID-19 Identification ResNet (CIdeR) on the INTERSPEECH COVID-19 from Audio Challenges},
  author = {Alican Akman and Harry Coppock and Alexander Gaskell and Panagiotis Tzirakis and Lyn Jones and Björn W. Schuller},
  journal= {arXiv preprint arXiv:2107.14549},
  year   = {2021}
}

Comments

5 pages, 1 figure